Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19167
    Prev
    Next
    INDEX
    Explanations

    words related to outdoor trails or paths

    oai_token-act-pair · gpt-3.5-turbo

    mentions of trails and related outdoor activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kamp
    -0.69
     Hague
    -0.65
    ately
    -0.64
     palp
    -0.63
    lesi
    -0.62
    ity
    -0.61
     Urs
    -0.60
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.59
    orporated
    -0.58
     tuition
    -0.57
    POSITIVE LOGITS
    bl
    1.26
     Blazers
    1.16
    head
    1.00
    roads
    0.95
    ways
    0.94
    heads
    0.94
    toe
    0.89
    runner
    0.84
    find
    0.84
    walker
    0.83
    Activations Density 0.026%

    No Known Activations